Update documentation

.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: a87963abbb1285ed80a6ead8e45657fa
+config: c107af7d3dded06e26715a49c95b6214
 tags: 645f666f9bcd5a90fca523b33c5a78b7

_panels_static/panels-variables.06eb56fa6e07937060861dad626602ad.css

@@ -0,0 +1,7 @@
+:root {
+--tabs-color-label-active: hsla(231, 99%, 66%, 1);
+--tabs-color-label-inactive: rgba(178, 206, 245, 0.62);
+--tabs-color-overline: rgb(207, 236, 238);
+--tabs-color-underline: rgb(207, 236, 238);
+--tabs-size-label: 1rem;
+}

_sources/README.md

@@ -2,7 +2,7 @@
 
 Developed for reproducible & reusable molecular QTL analyses for the NIH/NIA Alzheimer's Disease Sequencing Project (ADSP) Functional Genomics xQTL (FunGen-xQTL) Project.
 
-![QTL Diagram](code/images/complete_workflow.png)
+![QTL Diagram](code/images/xQTL_Protocol_June_2023.png)
 
 
 ## Overview of the protocol

_sources/code/data_preprocessing/genotype/GRM.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "bearing-strain",
+   "id": "constitutional-mining",
    "metadata": {
     "kernel": "SoS",
     "tags": []
@@ -15,7 +15,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "informed-outdoors",
+   "id": "objective-fitness",
    "metadata": {
     "kernel": "SoS"
    },
@@ -27,7 +27,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "recovered-steering",
+   "id": "independent-advertising",
    "metadata": {
     "kernel": "SoS",
     "tags": []
@@ -40,7 +40,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "enabling-gibraltar",
+   "id": "difficult-method",
    "metadata": {
     "kernel": "SoS",
     "tags": []
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "correct-commodity",
+   "id": "governmental-platinum",
    "metadata": {
     "kernel": "SoS"
    },
@@ -64,7 +64,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "modular-rogers",
+   "id": "affecting-johns",
    "metadata": {
     "kernel": "Bash"
    },
@@ -78,7 +78,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "religious-exhibition",
+   "id": "confused-contents",
    "metadata": {
     "kernel": "SoS"
    },
@@ -89,7 +89,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "coordinate-harvest",
+   "id": "worst-fossil",
    "metadata": {
     "kernel": "Bash"
    },
@@ -138,7 +138,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "norman-yield",
+   "id": "brief-extraction",
    "metadata": {
     "kernel": "SoS"
    },
@@ -149,7 +149,7 @@
     "parameter: cwd = path(\"output\")\n",
     "# The filename name for output data\n",
     "parameter: container = ''\n",
-    "parameter: entrypoint={('micromamba run -n' + ' ' + container.split('/')[-1][:-4]) if container.endswith('.sif') else f''}\n",
+    "parameter: entrypoint=('micromamba run -n' + ' ' + container.split('/')[-1][:-4] + \" --no-capture-output\") if container.endswith('.sif') else \"\"\n",
     "# For cluster jobs, number commands to run per job\n",
     "parameter: job_size = 1\n",
     "# Wall clock time expected\n",
@@ -215,7 +215,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "south-subscription",
+   "id": "opposed-function",
    "metadata": {
     "kernel": "SoS"
    },
@@ -239,7 +239,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "realistic-couple",
+   "id": "nominated-winner",
    "metadata": {
     "kernel": "SoS"
    },
@@ -256,7 +256,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "directed-penetration",
+   "id": "associate-turner",
    "metadata": {
     "kernel": "SoS"
    },
@@ -269,7 +269,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "described-zoning",
+   "id": "directed-cigarette",
    "metadata": {
     "kernel": "SoS"
    },
@@ -288,7 +288,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "hairy-popularity",
+   "id": "transparent-spencer",
    "metadata": {
     "kernel": "SoS"
    },
@@ -299,7 +299,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "expensive-gateway",
+   "id": "herbal-portugal",
    "metadata": {
     "kernel": "SoS"
    },
@@ -310,21 +310,33 @@
     "output: f'{_input:nn}.apex.grm'\n",
     "task: trunk_workers = 1, trunk_size = job_size, walltime = walltime, mem = mem, cores = numThreads, tags = f'{step_name}_{_output:bn}'\n",
     "R: expand= \"$[ ]\", stderr = f'{_output}.stderr', stdout = f'{_output}.stdout', container = container, entrypoint=entrypoint\n",
-    "   library(\"dplyr\")\n",
-    "   library(\"tibble\")\n",
-    "   library(\"readr\")\n",
-    "   library(\"purrr\")\n",
-    "    grm = read_delim(gzfile(\"$[_input]\"),\"\\t\",col_names = FALSE)\n",
-    "    id = unlist(read_delim(\"$[_input:n].id\",\"\\t\",col_names = FALSE)[,2])\n",
-    "    grm = grm[,c(1,2,4)]\n",
-    "    colnames(grm) = c(\"#id1\",\"id2\",\"kinship\")\n",
-    "    grm = grm%>%mutate(`#id1` = map_chr(`#id1`, ~id[.x]),`id2` =  map_chr(`id2`, ~id[.x]))\n",
-    "    grm%>%write_delim(\"$[_output]\",\"\\t\")"
+    "\n",
+    "    # Load necessary libraries\n",
+    "    library(dplyr)\n",
+    "    library(readr)\n",
+    "    library(purrr)\n",
+    "\n",
+    "    # Read data\n",
+    "    grm <- read_delim(gzfile(\"$[_input]\"), '\\t', col_names = FALSE) %>%\n",
+    "      select(1, 2, 4) %>%\n",
+    "      set_names(c(\"#id1\", \"id2\", \"kinship\"))\n",
+    "\n",
+    "    id <- read_delim(\"$[_input:n].id\", '\\t', col_names = FALSE)[, 2] %>%\n",
+    "      unlist()\n",
+    "\n",
+    "    # Modify grm data\n",
+    "    grm_updated <- grm %>%\n",
+    "      mutate(`#id1` = map_chr(`#id1`, ~id[.x]),\n",
+    "             `id2` = map_chr(`id2`, ~id[.x]))\n",
+    "\n",
+    "    # Write to output\n",
+    "    grm_updated %>%\n",
+    "      write_delim(\"$[_output]\", '\\t')"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "interracial-batch",
+   "id": "printable-freedom",
    "metadata": {
     "kernel": "SoS"
    },
@@ -335,7 +347,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "charming-samoa",
+   "id": "laden-salon",
    "metadata": {
     "kernel": "SoS"
    },
@@ -346,15 +358,25 @@
     "input: group_by = \"all\"\n",
     "output: f'{cwd}/{path(list(genotypes.values())[1]):bnn}.loco_grm_list.txt'\n",
     "R: expand= \"$[ ]\", stderr = f'{_output}.stderr', stdout = f'{_output}.stdout', container = container, entrypoint=entrypoint\n",
-    "    library(\"dplyr\")\n",
-    "    library(\"tibble\")\n",
-    "    library(\"readr\")\n",
-    "    library(\"purrr\")\n",
-    "    chrom = paste0(\"chr\",c($[paths(genotypes.keys()):r,]),collapse = \"\")\n",
-    "    files = c($[_input:r,])\n",
-    "    dir = \"$[_output:nn]\"\n",
-    "    grm_list = tibble(`#chr` = chrom, dir = files)%>%arrange(`#chr`)\n",
-    "    grm_list%>%write_delim(\"$[_output]\",\"\\t\")"
+    "\n",
+    "    # Load necessary libraries\n",
+    "    library(dplyr)\n",
+    "    library(readr)\n",
+    "    library(purrr)\n",
+    "\n",
+    "    # Define chromosomal names\n",
+    "    chromosomes <- paste0(\"chr\", c($[paths(genotypes.keys()):r,]), collapse = \"\")\n",
+    "\n",
+    "    # Define input files and directory\n",
+    "    input_files <- c($[_input:r,])\n",
+    "\n",
+    "    # Create and sort the tibble\n",
+    "    grm_tibble <- tibble(`#chr` = chromosomes, dir = input_files) %>%\n",
+    "      arrange(`#chr`)\n",
+    "\n",
+    "    # Write to output\n",
+    "    grm_tibble %>%\n",
+    "      write_delim(\"$[_output]\", \"\\t\")"
    ]
   }
  ],
@@ -389,7 +411,7 @@
      "sos"
     ]
    ],
-   "version": "0.24.1"
+   "version": "0.22.4"
   }
  },
  "nbformat": 4,